Predicting the way something will smell is incredibly complex. That’s because we perceive scents using the millions of sensory neurons in our brains—and because scents are multi-faceted. For example, how would you describe the smell of an orange? Sweet? Bright? Grassy? Each descriptor is unique. Classifying smell is tricky because it requires a multi-label system.
Researchers at Google are building graph neural networks—a particular type of deep neural network that operates on graphs as inputs—to predict odors at a molecular level.
This trend is part of our section on Artificial Intelligence. Other trends in this section include:
Advertising and Public Relations, Aerospace, Agriculture, Airlines, Alternative Energy Production & Services, Architectural Services, Auto Manufacturers, Banking, Beauty, Broadcasters, Radio and TV, Builders/General Contractors, Cable & Satellite TV Production & Distribution, Casinos/Gambling, Chemical & Related Manufacturing, Civil Servants/Public Officials, Clothing Manufacturing, Commercial TV & Radio Stations, Construction, Covid-19/ coronavirus, CPG, Cruise Ships & Lines, Defense, Doctors & Other Health Professionals, Drug Manufacturers, Education Colleges & Universities, Education Online, Education Trades, Electric Utilities, Entertainment Industry, Environment, Finance, Foreign & Defense Policy, Gas & Oil, Government - International, Government - National, Government - State and Local, Health Professionals, Hedge Funds, Human Resources, Information Technology, Infrastructure, Insurance, Law Enforcement, Lawyers/Law Firms/Legal Industry, Luxury Retail, Magazines, Manufacturing, National Security, News Media, Online Media, Pharmaceuticals/Health Products, Private Equity, Professional Services, Professional Sports, Radio/TV Stations, Real Estate, Retail, Telecommunications, Trade Associations, Travel Industry, TV Production, TV/Movies/Music, Utilities, Venture Capital, Waste Management, Work (Future of)